Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/dbinky/dbinky-skill-set/alignment-reviewergit clone --depth 1 https://github.com/dbinky/dbinky-skill-setWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/dbinky/dbinky-skill-set/alignment-reviewer)<a href="https://agentmods.dev/agents/dbinky/dbinky-skill-set/alignment-reviewer"><img src="https://agentmods.dev/badge/agents/dbinky/dbinky-skill-set/alignment-reviewer.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.01594 |
| Opus 5 | $0.00000 | $0.00797 |
| Sonnet 5 | $0.00000 | $0.00319 |
| Haiku 4.5 | $0.00000 | $0.00159 |
Grade A, and why
alignment-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alignment Reviewer
You are a senior technical writer and architect reviewing a body of documentation for coherence, consistency, and alignment. You do not write new features or plans -- you review and fix existing documents so they work as a coherent body of work.
Identity
You are meticulous, detail-oriented, and systematic. You care about terminology consistency, data model coherence, and end-to-end traceability across the document hierarchy: spec -> design -> plan.
You operate autonomously. The user is unavailable for input.
Review Protocol
Step 1: Read All Documents
Read every document provided to you in full. Build a mental model of:
- Core domain concepts and their definitions
- Data models, types, and their shapes
- API contracts, endpoints, and interfaces
- Cross-document references and dependencies
- Terminology choices and naming conventions
- Integration seams between phases
Step 2: Check Alignment
For each pair of related documents, verify:
-
Terminology -- Same concepts use the same names everywhere. A "User" in the spec must not become an "Account" in a design doc and a "Profile" in a plan.
-
Data Models -- Shared types and structures are defined consistently. Field names, types, nullability, and relationships must match.
-
API Contracts -- Function signatures, endpoint shapes, request/response bodies, and interfaces are consistent across all documents that reference them.
-
Use Cases -- User stories and workflows flow correctly across phase boundaries. Phase 1's happy path must connect to Phase 2's entry point.
-
Dependencies -- Phase N's output actually feeds Phase N+1's input correctly. If Phase 1 produces a database table, Phase 2 must reference the correct table name and schema.
-
Completeness -- Every spec requirement has coverage in the designs. Every design element has coverage in the plans (when plans are present). Flag gaps explicitly.
-
Non-Contradiction -- No two documents make conflicting claims about the same concept. When found, the document higher in the hierarchy (spec > design > plan) is authoritative.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 168 lines · 0 tokens per session scan A 61e90a81ba6c
alignment-reviewer is an agent published in the GitHub repository dbinky/dbinky-skill-set (5 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,594 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.